Suchi Saria is the John C. Malone Assistant Professor of computer science at the Whiting School of Engineering and of statistics and health policy at the Bloomberg School of Public Health. She directs the Machine Learning and Healthcare Lab and is the founding research director of the Malone Center for Engineering in Healthcare.
Saria’s goal is to use sophisticated computer science and the deluge of data available in health care and other settings to individualize patient care and to save lives. Her pioneering work centers on enabling new classes of diagnostic and treatment planning tools for health care—tools that use statistical machine-learning techniques to tease out subtle information from “messy” observational datasets, and provide reliable inferences for individualizing care decisions.
Saria’s work provides an entry point into a future in which the data collected from a large number of patients may reliably inform physicians about the best treatment plans for individual patients. For instance, algorithms that she created are being used today in hospitals to predict with startling accuracy which patients will succumb to deadly sepsis (a condition that annually kills more people than breast and prostate cancer combined)— work that led to her being named one of Popular Science magazine’s “Brilliant 10” (2016); one of MIT’s “35 Innovators Under 35” (2017); and a member of the World Economic Forum’s Young Global Leaders (2018).
For another project, Saria and her team created an app that allows patients with Parkinson’s disease to track their symptoms on their personal smartphones. Rather than relying on the subjective observations of a medical staff member in a clinical setting, giving patients the ability to report on their symptoms at any time of day, in a clinic or within their own home, can better capture the day-to-day variability of Parkinson’s symptoms and provide doctors with a clearer picture of their patients’ overall health and how well their medications are working.
This work is considered groundbreaking because though other mobile studies also collect data “in the wild,” few have found ways to validate it clinically because that process requires the expensive and laborious collection of benchmark (also called “gold standard”) data at home. Saria solved this issue by developing a machine learning framework that uses “weak supervision”—information that is inexpensive and readily collected at home—to train algorithms for progression monitoring from mobile data.
Saria’s work has received recognition including: best paper awards at machine learning, informatics, and medical venues; a Rambus Fellowship (2004-2010), an NSF Computing Innovation Fellowship (2011); selection by IEEE Intelligent Systems to Artificial Intelligence’s “10 to Watch” (2015); the DARPA Young Faculty Award (2016); and the Sloan Research Fellowship (2018).
In 2017, Saria’s work was among four research contributions presented by France Córdova, Director of the National Science Foundation, to the U.S. House of Representatives” Commerce, Justice Science Appropriations Committee.
She was invited to join the National Academy of Engineering’s Frontiers of Engineering program in 2017 and, in 2018, to join the National Academy of Medicine’s program for Emerging Leaders in Health and Medicine. Saria came to Johns Hopkins in 2012. Prior to that, she received her Ph.D. from Stanford University working with Daphne Koller.